<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fei-etal-2019-end">
    <titleInfo>
        <title>End-to-end Deep Reinforcement Learning Based Coreference Resolution</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hongliang</namePart>
        <namePart type="family">Fei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xu</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dingcheng</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ping</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Korhonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Traum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Màrquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recent neural network models have significantly advanced the task of coreference resolution. However, current neural coreference models are usually trained with heuristic loss functions that are computed over a sequence of local decisions. In this paper, we introduce an end-to-end reinforcement learning based coreference resolution model to directly optimize coreference evaluation metrics. Specifically, we modify the state-of-the-art higher-order mention ranking approach in Lee et al. (2018) to a reinforced policy gradient model by incorporating the reward associated with a sequence of coreference linking actions. Furthermore, we introduce maximum entropy regularization for adequate exploration to prevent the model from prematurely converging to a bad local optimum. Our proposed model achieves new state-of-the-art performance on the English OntoNotes v5.0 benchmark.</abstract>
    <identifier type="citekey">fei-etal-2019-end</identifier>
    <identifier type="doi">10.18653/v1/P19-1064</identifier>
    <location>
        <url>https://aclanthology.org/P19-1064</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>660</start>
            <end>665</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T End-to-end Deep Reinforcement Learning Based Coreference Resolution
%A Fei, Hongliang
%A Li, Xu
%A Li, Dingcheng
%A Li, Ping
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F fei-etal-2019-end
%X Recent neural network models have significantly advanced the task of coreference resolution. However, current neural coreference models are usually trained with heuristic loss functions that are computed over a sequence of local decisions. In this paper, we introduce an end-to-end reinforcement learning based coreference resolution model to directly optimize coreference evaluation metrics. Specifically, we modify the state-of-the-art higher-order mention ranking approach in Lee et al. (2018) to a reinforced policy gradient model by incorporating the reward associated with a sequence of coreference linking actions. Furthermore, we introduce maximum entropy regularization for adequate exploration to prevent the model from prematurely converging to a bad local optimum. Our proposed model achieves new state-of-the-art performance on the English OntoNotes v5.0 benchmark.
%R 10.18653/v1/P19-1064
%U https://aclanthology.org/P19-1064
%U https://doi.org/10.18653/v1/P19-1064
%P 660-665

Markdown (Informal)

[End-to-end Deep Reinforcement Learning Based Coreference Resolution](https://aclanthology.org/P19-1064) (Fei et al., ACL 2019)

• End-to-end Deep Reinforcement Learning Based Coreference Resolution (Fei et al., ACL 2019)

ACL

• Hongliang Fei, Xu Li, Dingcheng Li, and Ping Li. 2019. End-to-end Deep Reinforcement Learning Based Coreference Resolution. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 660–665, Florence, Italy. Association for Computational Linguistics.